Mass Storage System Research Articles

F-48 空気吹付け方式躯体蓄熱の熱負荷近似計算手法 : (第4報)各種条件における熱負荷の日変化曲線の作成

F-48 空気吹付け方式躯体蓄熱の熱負荷近似計算手法 : (第4報)各種条件における熱負荷の日変化曲線の作成

Fabrication of Beam-rotating Actuator for Multiple-beam Disk Drive

Current trends in computer and communication industries are towards increasingly higher resolution images and video processing techniques. However, such sophisticated processing tasks require massive storage systems such as a compact disk read only memory (CD-ROM) and digital versatile disc (DVD). Current demands in the development of such systems are higher data density storage media and an improved data transfer rate. The latter is discussed in this paper. A multiple-beam optical disk drive is presented as a method for improving the effective data transfer rate by increasing the beam spot number formed on an optical disk. The beam-rotating actuator is necessary for positioning the multiple-beam onto more than one track. Ray tracing was also employed for the real system setup. The beam-rotating actuator is made up of piezoelectric material, a high-stiffness wire hinge and a dove prism. The actuator has an approximately 1 kHz resonance frequency and a suitable operational range. The dynamic equation for the actuator is derived for the control of the real system.

The GIOD Project — Globally Interconnected Object Databases

The GIOD (Globally Interconnected Object Databases) Project, a joint effort between Caltech and CERN, funded by Hewlett Packard Corporation, has investigated the use of WAN-distributed Object Databases and Mass Storage systems for LHC data. A prototype small-scale LHC data analysis center has been constructed using computing resources at Caltechs Centre for Advanced Computing Research (CACR). These resources include a 256 CPU HP Exemplar of ∼4600 SPECfp95, a 600 TByte High Performance Storage System (HPSS), and local/wide area links based on OC3 ATM. Using the Exemplar, a large number of fully simulated CMS events were produced, and used to populate an object database with a complete schema for raw, reconstructed and analysis objects. The reconstruction software used for this task was based on early codes developed in preparation for the current CMS reconstruction program, ORCA. Simple analysis software was then developed in Java, and integrated with SLACs Java Analysis Studio tool. An event viewer was constructed with the Java 3D API. Using this suite of software, tests were made in collaboration with researchers at FNAL and SDSC, that focused on distributed access to the database by numerous clients, and measurements of peak bandwidths were made and interpreted. In this paper, some significant findings from the GIOD Project are presented, such as the achievement of the CMS experiment's 100 MB/s database I/O milestone.

The ALICE DAQ: current status and future challenges

The ALICE data acquisition system has been designed to support an aggregate event-building bandwidth of up to 2.5 GByte/s and a storage capability of up to 1.25 GByte/s to mass storage. A general framework called the ALICE Data Acquisition Test Environment (DATE) system has been developed as a basis for prototyping the components of the DAQ. DATE supports a wide spectrum of configurations from simple systems to more complex systems with multiple detectors and multiple event builders. Prototypes of several key components of the ALICE DAQ have been developed and integrated with the DATE system such as the ALICE Detector Data Link, the online data monitoring from ROOT and the interface to the mass storage systems. Combined tests of several of these components are being pursued during the ALICE Data Challenges. The architecture of the ALICE DAQ system will be presented together with the current status of the different prototypes. The recent addition of a Transition Radiation Detector (TRD) to ALICE has required a revision of the requirements and the architecture of the DAQ. This will allow for a higher level of data selection. These new opportunities and implementation challenges will also be presented.

Influence of active heat sinks on fabric thermal storage in building mass

There is an increasing drive towards low energy architecture and developing buildings that work with the climate rather than in spite of it. One technology in the area of low energy building design is that of utilising building thermal mass and/or active thermal storage systems. Essentially the mass acts as a thermal flywheel and can both attenuate external energy flows and suppress internal environmental energy swings. These active thermal storage systems can take differing configurations and in this paper the results and comparisons for a few differing geometries and configurations are presented. Relationships between slab surface temperature, cooling potential and active core temperature are also presented.

Experience with using CORBA to implement a file caching coordination system

AbstractWe describe our experience with using several CORBA products to interconnect the software modules of a fairly complex system for file caching coordination from a tertiary storage. The application area that the system was designed for is High Energy and Nuclear Physics (HENP). In this application area, the volume of data reaches hundreds of terabytes per year and therefore it is impractical to store them on disk systems. Rather the data are organized into large files and stored on robotic tape systems that are managed by some Mass Storage System (MSS). The role of the Storage Access Coordination System (STACS) that we developed is to manage the caching of files from the MSS to a large disk cache that is shared by multiple HENP analysis programs. The system design involved multiple components developed by different people at different sites and the modules could potentially be distributed as well. In this paper we describe the architecture and implementation of STACS, emphasizing the inter‐module communication requirements. We describe the use of CORBA interfaces between system components, and our experience with using multi‐threaded CORBA and using hundreds of concurrent CORBA connections. STACS development was recently completed and is being incorporated in an operational environment that started to produce data in the summer of 2000 [1]. Copyright © 2001 John Wiley & Sons, Ltd.

Prediction and Load Balancing System for Distributed Storage

National Data Storage is a distributed data storage system intended to provide high quality backup, archiving and data access services. These services guarantee high level of data protection as well as high performance of data storing and retrieval by using replication techniques. Monitoring and data access prediction are necessary for successful deployment of replication. Common Mass Storage System Model (CMSSM) is used to present a storage performance view of storage nodes in unified way for monitoring and prediction purposes. %for heterogenios data storage systems. In this paper some conceptual and implementation details on using CMSSM for creating a Prediction and Load Balancing Subsystem for replica management are presented. Real system test results are also shown.

MEMS-based integrated-circuit mass-storage systems

MEMS-based integrated-circuit mass-storage systems

Rapid framing mass storage system on the internet

Mass storage system is now very important for storing huge volume of data in many application system such as VOD systems, electronic library, scientific computation and so on. Besides the storage device and network devices, the real performance of mass storage system is greatly influenced by the connection way between the host and storage system. Here we propose a new design of mass storage system by promoting the storage devices' functions and involving, them directly into data delivering. It can easily meet the demands both for capacity and I/O bandwidth in those applications, and has better service quality and performance compared with the traditional system in delivering mass data over network.

C-6 空気吹付け方式躯体蓄熱空調システムの性能実測 : (第2報)躯体蓄熱効率の統計的算出手法

C-6 空気吹付け方式躯体蓄熱空調システムの性能実測 : (第2報)躯体蓄熱効率の統計的算出手法

Design and evaluation of a generic software architecture for on-demand video servers

Introduces the design, implementation and evaluation of a generic software architecture for on-demand video servers. We describe different key components for controlling the storage and network devices within the server. The interactive collaborations between these software components are also illustrated. The experimental results indicate a very promising direction in exploring the right combinations of these software components. The server is thus able to increase the number of concurrent video accesses with the same hardware configuration. For instance, with the right combinations, the system achieved about 80% of the storage system bandwidth of four disks, about 70% of the storage system bandwidth of six disks, and generally reached the maximal achieved SCSI bandwidth when eight disks are used over two SCSI buses. Our research and experimental results are based on video servers currently under construction across a variety of hardware platforms, including SMP, DMP and clusters of PCs or workstations. The most advanced prototype server is based on an SGI shared-memory multiprocessor with a mass storage system consisting of RAID-3 disk arrays. With all the enabling/management schemes, we were able to further investigate interesting research issues by considering the user's access profiles for taking advantage of popular video titles. The results were significant, with a range of 60% improvement given a 512 kByte block size. In addition to the experimental results, theoretical performance models were also developed that closely match to our collected experimental results.

A distributed disk layer for mass storage at DESY

For the mass storage system at DESY, a disk layer is under development. Decoupling the client request queue and access to the mass storage system by means of migration, staging and prefetching it shall provide full utilization of robot and drive resources. By managing distributed disk resources in the heterogeneous computing environment of DESY, optimized data access shall be given.

Computing at KEK

In 1996 and in 1997, the KEK Computing Research Center installed two large UNIX workgroup cluster systems. Computing and data storage resources are partitioned and allocated to each research group with independent DCE cell administration. Data transfer between different workgroup clusters are established with inter-cell communication. These systems are the largest installation of DCE and DFS which are being used in production, in combination with the hierarchical storage management software on 20-TB and 160-TB tape library mass storage systems.

Mass storage system reduces aero engine development time

Mass storage system reduces aero engine development time

Global Network Access and Publication of Survey Data

The results of astronomical surveys include 1) catalogs containing anywhere from a few to many million objects, 2) data products used to generate the catalogs (e.g., images or spectra), 3) publications and 4) object based compilations of information from many sources. The ubiquitous growth in the Internet and the dramatic reduction in the cost of mass storage systems now allows instant global access to this information. Astrophysics on-line services have grown up with the Internet, and represent an invaluable resource whose access is a routine part of any research project. Unfortunately users are also faced with searching and accessing multiple sites with different content, access and response methods. There can also be inconsistencies amongst the various systems, which can involve extra effort to resolve. A network-integrated astrophysics system has long been sought because it would remove multiple user interfaces and allow much simpler integration of services. In an era of shrinking budgets, the issue is how to achieve this in a cost effective manner. This review gives an overview of the current situation and discusses the likely evolution towards a network-integrated astrophysics system.

Building video-on-demand servers

We have designed and implemented a controllable software architecture for a Video?on?Demand (VOD) server. With the proposed software architecture, many system design issues can be investigated. For example, we studied several disk striping schemes in the storage subsystem and examined the impact of the disk striping schemes on the utilization of system resources. In the processing component, we observed that additional concurrent video streams can be supported by using efficient memory interleaving. Buffering with a large memory space in the processing subsystem is a common technique to alleviate the latency variance of accessing different system components. By employing user?level control and scheduling, the variance can be decreased thereby reducing the resulting buffer space needed for each video stream. In the network subsystem, we adopted a server?driven approach for investigating MPEG?2 video delivery over Asynchronous Transfer Mode (ATM) networks. The VOD server controls the pace of video transmission and reduces the complexity of the client. Since the client has limited buffer space (due to cost considerations), we have reduced the buffer requirement by regulating the transmission based on timing information embedded in the MPEG?2 streams. Our research and experimental results are based on a VOD server which is currently under construction. The prototype server is based on an SGI shared?memory multiprocessor with a mass storage system consisting of RAID?3 disk arrays. Using 30 RAID?3 disk arrays, preliminary experimental results show that the prototype server can potentially support more than 360 high?quality video streams with careful design and coordination of the different system components.

Pythia and Pythia/WK: tools for the performance analysis of mass storage systems

The constant growth on the demands imposed on hierarchical mass storage systems creates a need for frequent reconfiguration and upgrading to ensure that the response times and other performance metrics are within the desired service levels. This paper describes the design and operation of two tools, Pythia and Pythia/WK, that assist system managers and integrators in making cost-effective procurement decisions. Pythia automatically buids and solves an analytic model of a mass storage system based on a graphical description of the architecture of the system, and on a description of the workload imposed on the system. The use of a modeling wizard to perform this conversion from a graphical description of a mass storage system to an analytic model makes Pythia unique among analytic performance tools. Pythia/WK uses clustering algorithms to characterize the workload from the log files of the mass storage system. The resulting workload characterization is used as input to Pythia. © 1997 John Wiley & Sons, Ltd.

Performance analysis of a storage hierarchy for video servers

With the aim of developing a video server architecture that satisfies incoming requests without delay, has very large storage capacity, and is cost effective, this paper evaluates the performance of a hierarchical video server storage system that consists of magnetic disk arrays and a tertiary mass storage system. The optimum hardware configuration and video file allocation are identified for files allocated to magnetic disk arrays in order of access frequency by running a series of simulations to satisfy a specified average waiting time constraint. It is shown by a numerical example that, when video files are partitioned for storage with a leader stored on faster magnetic disk arrays and the rest of the file stored on a mass storage system, there is an optimum file allocation where the average waiting time until playback of a requested video stream is minimized. Finally, it is quantitatively demonstrated that the storage unit cost ratio of a two-level hierarchical storage system combining faster magnetic disk arrays with a slower mass storage system is superior to that of a storage system configured out of magnetic disks alone.

A hierarchical network storage architecture for video-on-demand services

The advances in cable TV networks and multimedia technologies have open the possibilities for network/service/content providers to offer residential customers with video-on-demand services. However, the mass storage system used in supporting such services demands proper organization and management. We present a three-level hierarchical network storage architecture for the video-on-demand storage system. At the first-level (local service center, LSC) a limited number of programs with high viewing probabilities are stored; while at the second-level (local central service center, LCSC) a few programs with the second highest viewing probabilities are stored. The third-level (central service center, CSC) contains all programs provided in the system. Based on this architecture and the program viewing probability distribution function, we use a minimum-cost function to find out the number of programs stored in the two service centers (LSC and LCSC) and the number of links among these three service centers. We also describe two program reallocation algorithms which swap programs between service centers according to the change in user request patterns.

Analytical performance modeling of hierarchical mass storage systems

Mass storage systems are finding greater use in scientific computing research environments for retrieving and archiving the large volumes of data generated and manipulated by scientific computations. This paper presents a queuing network model that can be used to carry out capacity planning studies of hierarchical mass storage systems. Measurements taken on a Unitree mass storage system and a detailed workload characterization provided the workload intensity and resource demand parameters for the various types of read and write requests. The performance model developed here is based on approximations to multiclass Mean Value Analysis of queuing networks. The approximations were validated through the use of discrete event simulation and the complete model was validated and calibrated through measurements. The resulting model was used to analyze three different scenarios: effect of workload intensity increase, use of file compression at the server and client, and use of file abstractions.